サイト内検索
AI モデル 84762
- distil-whisper-large-v3-int8-ov↗
OpenVINO
This is distil-large-v3 model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF. The original model is distributed under mit license. More details can be found in original model card. Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.
- tiny-random-glm4↗
optimum-intel-internal-testing
- qwen2.5-1.5b-instruct-43-layers-zeroed↗
PJMixers-Dev
- Heejindo_-_rationale_model_e3_save5000_f4-gguf↗
RichardErkhov
- Smashitup_-_FineLlama-3.1-8B-q5_k_m-GGUF-gguf↗
RichardErkhov
- toastloaf_-_autotrain-gpt2-finetune-crab-4batches-gguf↗
RichardErkhov
- Qwen3.6-35B-Opus-Reasoning-GGUF↗
rico03
- granite-4.0-h-small-heretic-high-GGUF↗
rodrigomt
- reazonspeech-nemo-v2-GGUF↗
sakasegawa
- codegen-350M-mono↗
Salesforce
CodeGen is a family of autoregressive language models for **program synthesis** from the paper: A Conversational Paradigm for Program Synthesis by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong. The models are originally released in this repository, under 3 pre-training data variants (`NL`, `Multi`, `Mono`) and 4 model size variants (`350M`, `2B`, `6B`, `16B`). The checkpoint included in this repository is denoted as **CodeGen-Mono 350M** in the paper, where "Mono" means the model is initialized with *CodeGen-Multi 350M* and further pre-trained on a Python programming language dataset, and "350M" refers to the number of trainable parameters. This checkpoint (CodeGen-Mono 350M) was firstly initialized with *CodeGen-Multi 350M*, and then pre-trained on BigPython dataset. The data consists of 71.7B tokens of Python programming language. See Section 2.1 of the paper for more details.
